# The World Happiness Report determines the state of global happiness. 

# The happiness scores and rankings data has been collected by asking individuals to rank their life.

# Ranking ranges from 0 (worst possible life) to 10 (best possible life). 

​

import pandas as pd

import numpy as np

import seaborn as sns

import matplotlib.pyplot as plt

import plotly.express as px

import warnings

warnings.filterwarnings("ignore")

​

from jupyterthemes import jtplot

jtplot.style(theme = 'monokai', context = 'notebook', ticks = True, grid = False)

# Import csv file into pandas dataframe

happy_df = pd.read_csv('happiness_report.csv')

happy_df

# print the first 5 rows of the dataframe

happy_df.head()

happy_df.tail(8)

happy_df[  happy_df['Country or region'] == 'Canada' ]

happy_df[  happy_df['Country or region'] == 'Syria' ]

# Check the number of non-null values in the dataframe

happy_df.info()

# Check Null values

happy_df.isnull().sum()

# Obtain the Statistical summary of the dataframe

happy_df.describe()

# check the number of duplicated entries in the dataframe

happy_df.duplicated().sum() # since there are no duplicates, no further action is required

happy_df['Score'].max()

happy_df[happy_df['Score'] == 7.769]

# A scatterplot matrix is a matrix associated to n numerical arrays (data variables), $X_1,X_2,…,X_n$ , of the same length. 

# The cell (i,j) of such a matrix displays the scatter plot of the variable Xi versus Xj.

# Here we show the Plotly Express function px.scatter_matrix to plot the scatter matrix for the columns of the dataframe. By default, all columns are considered.

​

# Note:

# Positive correlation between GDP and score 

# Positive correlation between Social Support and score 

​

​

fig = px.scatter_matrix(happy_df[['Score','GDP per capita', 'Social support', 'Healthy life expectancy', 

    'Freedom to make life choices', 'Generosity', 'Perceptions of corruption']], width = 1500, height = 1500)

fig.show()

# Alternatively, you can use Seaborn to plot the pairplots as follows (Note that the plot is no longer interactive): 

fig = plt.figure(figsize = (20,20))

sns.pairplot(happy_df[['Score','GDP per capita', 'Social support', 'Healthy life expectancy', 

    'Freedom to make life choices', 'Generosity', 'Perceptions of corruption']])

​

# Positive correlation between GDP and score 

# Positive correlation between Social Support and score 

​

# distplot combines the matplotlib.hist function with seaborn kdeplot()

​

columns = ['Score','GDP per capita', 'Social support', 'Healthy life expectancy', 'Freedom to make life choices', 'Generosity',

       'Perceptions of corruption']

​

plt.figure(figsize = (20, 50))

for i in range(len(columns)):

  plt.subplot(8, 2, i+1)

  sns.distplot(happy_df[columns[i]], color = 'g');

  plt.title(columns[i])

​

plt.tight_layout()

happy_df.corr()

fig = px.imshow(happy_df.corr())

fig.show()

# Get the correlation matrix

corr_matrix = happy_df.corr()

corr_matrix

sns.heatmap(corr_matrix, annot = True)

# Plot the relationship between score, GDP and region

fig = px.scatter(happy_df, x = 'GDP per capita', y = 'Score', text = 'Country or region')

fig.update_traces(textposition = 'top center')

fig.update_layout(height = 1000)

fig.show()

# Plot the relationship between score and GDP (while adding color and size)

fig = px.scatter(happy_df, x = "GDP per capita", y = "Score", size = 'Overall rank', color = "Country or region", hover_name = "Country or region")

​

fig.update_layout(title_text = 'Happiness Score vs GDP per Capita')

fig.show()